{"id":"https://openalex.org/W3161127962","doi":"https://doi.org/10.1109/icassp39728.2021.9414626","title":"Generating Human Readable Transcript for Automatic Speech Recognition with Pre-Trained Language Model","display_name":"Generating Human Readable Transcript for Automatic Speech Recognition with Pre-Trained Language Model","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161127962","doi":"https://doi.org/10.1109/icassp39728.2021.9414626","mag":"3161127962"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078591720","display_name":"Junwei Liao","orcid":"https://orcid.org/0000-0001-7321-7583"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junwei Liao","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101597408","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0003-1872-3429"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Microsoft Cognitive Services Research Group,USA","Microsoft Cognitive Services Research Group, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cognitive Services Research Group,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Cognitive Services Research Group, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640051","display_name":"Ming Gong","orcid":"https://orcid.org/0000-0001-6140-7187"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Gong","raw_affiliation_strings":["Microsoft STCA NLP Group"],"affiliations":[{"raw_affiliation_string":"Microsoft STCA NLP Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077262995","display_name":"Linjun Shou","orcid":"https://orcid.org/0000-0002-1050-7708"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linjun Shou","raw_affiliation_strings":["Microsoft STCA NLP Group"],"affiliations":[{"raw_affiliation_string":"Microsoft STCA NLP Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sefik Eskimez","raw_affiliation_strings":["Microsoft Cognitive Services Research Group,USA","Microsoft Cognitive Services Research Group, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cognitive Services Research Group,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Cognitive Services Research Group, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102933609","display_name":"Liyang Lu","orcid":"https://orcid.org/0000-0001-5003-7459"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liyang Lu","raw_affiliation_strings":["Microsoft Cognitive Services Research Group,USA","Microsoft Cognitive Services Research Group, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cognitive Services Research Group,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Cognitive Services Research Group, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021975286","display_name":"Hong Qu","orcid":"https://orcid.org/0000-0001-6114-3441"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Qu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089195158","display_name":"Michael Zeng","orcid":"https://orcid.org/0000-0001-5302-5883"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Zeng","raw_affiliation_strings":["Microsoft Cognitive Services Research Group,USA","Microsoft Cognitive Services Research Group, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Cognitive Services Research Group,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Cognitive Services Research Group, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5078591720"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.6798,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74954385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7578","last_page":"7582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.88716059923172},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6775884032249451},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6772741079330444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6557365655899048},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5428126454353333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5271289944648743},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.5228753089904785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5158140063285828},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.515745222568512},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5109562277793884},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4293571710586548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.88716059923172},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6775884032249451},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6772741079330444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6557365655899048},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5428126454353333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5271289944648743},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.5228753089904785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5158140063285828},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.515745222568512},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5109562277793884},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4293571710586548},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W26608090","https://openalex.org/W98892075","https://openalex.org/W196317654","https://openalex.org/W2101105183","https://openalex.org/W2113410090","https://openalex.org/W2396384435","https://openalex.org/W2402268235","https://openalex.org/W2896457183","https://openalex.org/W2916979304","https://openalex.org/W2939248538","https://openalex.org/W2945260553","https://openalex.org/W2963341956","https://openalex.org/W2964243274","https://openalex.org/W2965373594","https://openalex.org/W2970868759","https://openalex.org/W2971274815","https://openalex.org/W2972529197","https://openalex.org/W3015722595","https://openalex.org/W3015752032","https://openalex.org/W3208272311","https://openalex.org/W6601052561","https://openalex.org/W6604003587","https://openalex.org/W6607995579","https://openalex.org/W6713098461","https://openalex.org/W6755207826","https://openalex.org/W6762122294","https://openalex.org/W6766673545","https://openalex.org/W6767485738","https://openalex.org/W6775945549","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2032810564","https://openalex.org/W2370831213","https://openalex.org/W2972807713","https://openalex.org/W4315704968","https://openalex.org/W2100255360","https://openalex.org/W2107506952","https://openalex.org/W3135287016"],"abstract_inverted_index":{"Modern":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems":[5],"can":[6,21,175],"achieve":[7],"high":[8],"performance":[9],"in":[10,35,69],"terms":[11],"of":[12,48,157],"recognition":[13],"accuracy.":[14],"However,":[15],"a":[16,92,109,122,129,147,154],"perfectly":[17],"accurate":[18],"transcript":[19],"still":[20],"be":[22,63],"challenging":[23],"to":[24,27,65,83,107,133],"read":[25],"due":[26],"disfluency,":[28],"filter":[29],"words,":[30],"and":[31,41,58,87,97,127,163],"other":[32],"errata":[33],"common":[34],"spoken":[36],"communication.":[37],"Many":[38],"downstream":[39,98],"tasks":[40],"human":[42],"readers":[43],"rely":[44],"on":[45,159,165],"the":[46,49,56,66,70,85,102,116,135,140,181],"output":[47,90],"ASR":[50,59,78,89],"system;":[51],"therefore,":[52],"errors":[53],"introduced":[54],"by":[55,153],"speaker":[57],"system":[60],"alike":[61],"will":[62],"propagated":[64],"next":[67],"task":[68],"pipeline.":[71],"In":[72],"this":[73],"work,":[74],"we":[75,120],"propose":[76,121],"an":[77],"post-processing":[79,151],"model":[80,145],"that":[81,172],"aims":[82],"transform":[84],"incorrect":[86],"noisy":[88],"into":[91],"readable":[93],"text":[94],"for":[95,112],"humans":[96],"tasks.":[99],"We":[100],"leverage":[101],"Metadata":[103],"Extraction":[104],"(MDE)":[105],"corpus":[106],"construct":[108],"task-specific":[110],"dataset":[111,117],"our":[113,144,173],"study.":[114],"Since":[115],"is":[118],"small,":[119],"novel":[123],"data":[124],"augmentation":[125],"method":[126,152,174],"use":[128],"two-stage":[130],"training":[131],"strategy":[132],"fine-tune":[134],"RoBERTa":[136],"pre-trained":[137],"model.":[138],"On":[139],"constructed":[141],"test":[142],"set,":[143],"outperforms":[146],"production":[148],"two-step":[149],"pipeline-based":[150],"large":[155],"margin":[156],"13.26":[158],"readability-aware":[160],"WER":[161],"(RA-WER)":[162],"17.53":[164],"BLEU":[166],"metrics.":[167],"Human":[168],"evaluation":[169],"also":[170],"demonstrates":[171],"generate":[176],"more":[177],"human-readable":[178],"transcripts":[179],"than":[180],"baseline":[182],"method.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}